Unobtrusive Fall Detection Using 3D Images of a Gaming Console: Concept and First Results

Image based fall detection is costly and rated obtrusive by those being monitored. The approach presented in this paper uses a cost efficient gaming console for 3D image generation. The image itself covers a range of about up to 30cm above the floor and allows for a nearly invisible positioning e.g. under the bed. Image analysis allows classifying events like “feet in front of the bed”, “fall”, “leaving the room” and “activity in the room”. For use in nursing homes and in home environments a system design has been implemented which is compatible with the guidelines of the Continua Health Alliance and fulfils data privacy requirements. The system supports the nursing home in its obligations for documentation of events. It was successfully tested in a laboratory environment and in a small scale test using three rooms of a nursing home in order to prepare for a large scale trial.